Search Results for author: Ewa Kijak

Found 17 papers, 4 papers with code

Which Discriminator for Cooperative Text Generation?

1 code implementation25 Apr 2022 Antoine Chaffin, Thomas Scialom, Sylvain Lamprier, Jacopo Staiano, Benjamin Piwowarski, Ewa Kijak, Vincent Claveau

Language models generate texts by successively predicting probability distributions for next tokens given past ones.

Language Modelling Text Generation

Generative Cooperative Networks for Natural Language Generation

no code implementations28 Jan 2022 Sylvain Lamprier, Thomas Scialom, Antoine Chaffin, Vincent Claveau, Ewa Kijak, Jacopo Staiano, Benjamin Piwowarski

Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation.

Image Generation Text Generation

AlignMix: Improving representations by interpolating aligned features

no code implementations29 Sep 2021 Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.

Data Augmentation Representation Learning

It Takes Two to Tango: Mixup for Deep Metric Learning

1 code implementation ICLR 2022 Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, Yannis Avrithis

In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time.

Ranked #4 on Metric Learning on In-Shop (using extra training data)

Data Augmentation Metric Learning +1

AlignMixup: Improving Representations By Interpolating Aligned Features

1 code implementation29 Mar 2021 Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels.

Data Augmentation Representation Learning +1

Detecting Human-Object Interaction with Mixed Supervision

no code implementations10 Nov 2020 Suresh Kirthi Kumaraswamy, Miaojing Shi, Ewa Kijak

Human object interaction (HOI) detection is an important task in image understanding and reasoning.

Human-Object Interaction Detection

Unsupervised part learning for visual recognition

no code implementations CVPR 2017 Ronan Sicre, Yannis Avrithis, Ewa Kijak, Frederic Jurie

This strategy opens the door to the use of PBM in new applications for which the notion of image categories is irrelevant, such as instance-based image retrieval, for example.

Classification General Classification +2

Direct vs. indirect evaluation of distributional thesauri

no code implementations COLING 2016 Vincent Claveau, Ewa Kijak

In this paper, we address the problem of the evaluation of such thesauri or embedding models and compare their results.

Information Retrieval

M\'edias traditionnels, m\'edias sociaux : caract\'eriser la r\'einformation (Traditional medias, social medias : characterizing reinformation)

no code implementations JEPTALNRECITAL 2016 C{\'e}dric Maigrot, Ewa Kijak, Vincent Claveau

Nous pr{\'e}sentons d{'}autre part quelques exp{\'e}riences de d{\'e}tection automatique des messages issus des m{\'e}dias de r{\'e}information, en {\'e}tudiant notamment l{'}influence d{'}attributs de surface et d{'}attributs portant plus sp{\'e}cifiquement sur le contenu de ces messages.

SENTER SENTS

Distributional Thesauri for Information Retrieval and vice versa

no code implementations LREC 2016 Vincent Claveau, Ewa Kijak

In this paper, we address the problem of building and evaluating such thesauri with the help of Information Retrieval (IR) concepts.

Information Retrieval

Strat\'egies de s\'election des exemples pour l'apprentissage actif avec des champs al\'eatoires conditionnels

no code implementations JEPTALNRECITAL 2015 Vincent Claveau, Ewa Kijak

D{'}autre part, nous d{\'e}taillons une m{\'e}thode originale de s{\'e}lection s{'}appuyant sur un crit{\`e}re de respect des proportions dans les jeux de donn{\'e}es manipul{\'e}s. Le bien- fond{\'e} de ces propositions est v{\'e}rifi{\'e} au travers de plusieurs t{\^a}ches et jeux de donn{\'e}es, incluant reconnaissance d{'}entit{\'e}s nomm{\'e}es, chunking, phon{\'e}tisation, d{\'e}sambigu{\"\i}sation de sens.

Active Learning Chunking

Generating and using probabilistic morphological resources for the biomedical domain

no code implementations LREC 2014 Vincent Claveau, Ewa Kijak

In most Indo-European languages, many biomedical terms are rich morphological structures composed of several constituents mainly originating from Greek or Latin.

Information Retrieval Machine Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.